Stronger data poisoning attacks break data sanitization defenses

DOI10.1007/s10994-021-06119-yOpenAlexW3217417806MaRDI QIDQ2127214

Jacob Steinhardt, Pang Wei Koh, Percy Liang

Publication date: 20 April 2022

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.00741

zbMATH Keywords

securityanomaly detectiondata poisoningdata sanitization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (2)

Random Projection and Recovery for High Dimensional Optimization with Arbitrary Outliers ⋮ Unnamed Item

Uses Software

• DeepFool
• AdaGrad
• IMDB
• BadNets
• Sever

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Notes about the Carathéodory number
• Some properties of the bilevel programming problem
• Practical bilevel optimization. Algorithms and applications
• The security of machine learning
• A survey of outlier detection methodologies
• Learning in the Presence of Malicious Errors
• The Power of Localization for Efficiently Learning Linear Separators with Noise
• On Agnostic Learning of Parities, Monomials, and Halfspaces
• Hardness of Learning Halfspaces with Noise
• Robust Estimators in High-Dimensions Without the Computational Intractability
• Learning from untrusted data
• Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers
• Learning geometric concepts with nasty noise
• On the learnability and design of output codes for multiclass problems

This page was built for publication: Stronger data poisoning attacks break data sanitization defenses